TEXT EXTRACTION FROM PALM LEAF MANUSCRIPTS

Abstract

Text extraction is a very important step in language processing and pattern recognition. The primary objective of this work is to extract text from the palm leaf manuscripts. The two color spaces used here are very standard ones as in BGR color space and HSV color space which stands for Blue, Green, Red and Hue, Saturation, Value respectively. The method proposed here first converts the images to the HSV color space and then their Hue, Value, and Saturation is varied manually with the help of the slide-bars introduced. The experimental results show the algorithm used to extract the text of a palm leaf manuscript performs fairly well.